Update README.md

README.md

@@ -19,6 +19,7 @@ tags:
 - disputes
 - refunds
 - agents
+- agentkit
 - trl
 - web3
 - usdc
@@ -29,10 +30,10 @@ tags:
 - text-generation
 ---
 
-# 🛡️ SRA-RiskGate-4B
+# 🛡️️ SRA-RiskGate-4B
 
 [![PyPI Version](https://img.shields.io/pypi/v/sra-riskgate?style=for-the-badge&logo=pypi&color=blue)](https://pypi.org/project/sra-riskgate/)
-[![PyPI Downloads](https://img.shields.io/pypi/dm/sra-riskgate?style=for-the-badge&logo=pypi&color=orange)](https://pypi.org/project/sra-riskgate/)
+[![PyPI Downloads](https://img.shields.io/pypi/dm/sra-riskgate?style=for-the-badge&logo=orange)](https://pypi.org/project/sra-riskgate/)
 [![Interactive Demo](https://img.shields.io/badge/Demo-Interactive%20Space-blue?style=for-the-badge&logo=huggingface)](https://sriram1983007-sra-riskgate-demo.static.hf.space/index.html)
 [![Dataset](https://img.shields.io/badge/Dataset-Risk%20Bench-green?style=for-the-badge&logo=huggingface)](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench)
 [![GGUF Quantized](https://img.shields.io/badge/GGUF-Q4__K__M-yellow?style=for-the-badge&logo=huggingface)](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF)
@@ -47,6 +48,57 @@ It is engineered for both ends of a stablecoin payment's operational lifecycle:
 
 ---
 
+## 🤖 Autonomous Agent Firewall (Coinbase AgentKit Integration)
+
+Autonomous on-chain agents can hallucinate payment transfers, sign malformed calldata, or trigger catastrophic transactions during market depegs. 
+
+The deterministic pre-filter and policy firewall is available directly as a plug-and-play **Action Provider** for the [Coinbase AgentKit](https://github.com/coinbase/agentkit) framework:
+
+```bash
+pip install "sra-riskgate[agentkit]>=0.3.3"
+
+```
+
+### Drop-in Agent Firewall Example
+
+Add `RiskGateActionProvider` to intercept and gate transaction attempts before wallet signing:
+
+```python
+from coinbase_agentkit import AgentKit, CdpWalletProvider, CdpWalletProviderConfig
+from sra_riskgate.integrations.agentkit import RiskGateActionProvider
+
+# 1. Initialize your wallet provider
+wallet_provider = CdpWalletProvider(CdpWalletProviderConfig())
+
+# 2. Wrap agent execution with the deterministic RiskGate firewall
+agentkit = AgentKit(
+    ActionProviderOptions(
+        wallet_provider=wallet_provider,
+        action_providers=[
+            RiskGateActionProvider(
+                max_amount=1000.0,      # Ceiling per transaction (USDC)
+                depeg_hold_pct=1.0,      # Triggers manual review if depeg >= 1%
+                depeg_reject_pct=5.0     # Hard aborts execution if depeg >= 5%
+            )
+        ]
+    )
+)
+
+```
+
+### Deterministic Risk Enforcement
+
+Every payment action triggered by the LLM is intercepted and validated against strict financial safety boundaries:
+
+| Check | Action Taken | Why It Matters |
+| --- | --- | --- |
+| **Invalid / Zero Address** | Hard Reject | Aborts `0x0...0` burner or malformed hex executions |
+| **Self-Transfer** | Hard Reject | Blocks recursive/hallucinated self-loops draining gas |
+| **Exceeds Amount Ceiling** | Paused (HOLD) | Intercepts rogue agent spending beyond allocated policy |
+| **Severe Depeg ($\ge 5\%$)** | Critical Abort | Prevents clearing payments in collapsing or compromised assets |
+
+---
+
 ## 🚀 Transformers Quickstart
 
 The model expects the standard ChatML template and outputs strict JSON conforming to the [sra-stablecoin-risk-bench](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench) schema:
@@ -163,6 +215,7 @@ with torch.no_grad():
 
 response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
 print(json.dumps(json.loads(response), indent=2))
+
 ```
 
 ### Output Schema (`risk_gate`)
@@ -181,6 +234,7 @@ print(json.dumps(json.loads(response), indent=2))
     "obtain_attestation_from_trusted_attester"
   ]
 }
+
 ```
 
 ---
@@ -191,6 +245,7 @@ The `sra-riskgate` SDK provides zero-latency deterministic pre-filtering rules (
 
 ```bash
 pip install --upgrade sra-riskgate
+
 ```
 
 ```python
@@ -208,11 +263,12 @@ tx = TransactionPayload(
 )
 
 verdict = gate.inspect(tx)
-print("Decision:       ", verdict.decision.value)       # hold
-print("Risk Score:     ", verdict.risk_score)           # 0.65
-print("Flags:          ", verdict.flags)                # ['MODERATE_DEPEG']
-print("Required Actions:", verdict.required_actions)     # ['manual_review']
-print("Explanation:    ", verdict.explanation)
+print("Decision:        ", verdict.decision.value)        # hold
+print("Risk Score:      ", verdict.risk_score)            # 0.65
+print("Flags:           ", verdict.flags)                 # ['MODERATE_DEPEG']
+print("Required Actions:", verdict.required_actions)      # ['manual_review']
+print("Explanation:     ", verdict.explanation)
+
 ```
 
 ---
@@ -223,11 +279,13 @@ Run locally via Ollama with greedy sampling (`temperature 0.0`) to ensure valid
 
 ```bash
 ollama run sriram1983007/sra-riskgate
+
 ```
 
 *Note: Ensure `temperature 0.0` is configured in your `Modelfile`.*
 
 ---
+
 ## 📊 Benchmark Evaluation (Held-Out Test Split)
 
 Evaluated against the 2,000-case test set in [`sra-stablecoin-risk-bench`](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench) using `score.py`:
@@ -252,4 +310,4 @@ Evaluated against the 2,000-case test set in [`sra-stablecoin-risk-bench`](https
 
 ## ⚖️ License
 
-Distributed under the Apache 2.0 License.
+Distributed under the Apache 2.0 License.